ClawHub
Back to skill

Security audit

Proxygate

Security checks for vulnerabilities and agentic risk

Overview

This ProxyGate router is not malicious, but its broad triggers could route unrelated requests into skills that may touch wallets, payments, tunnels, listings, and jobs.

Install only if you intend ProxyGate-specific routing. Before allowing downstream sub-skills to use wallets, payments, tunnels, listings, withdrawals, or job actions, verify the user explicitly asked for ProxyGate and require confirmation for account-changing or financial operations.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill description and trigger guidance use very broad terms such as 'buyers', 'sellers', 'jobs', 'status', and 'ProxyGate platform' topics, which can cause the router skill to activate for loosely related user requests. In an agent system, overbroad routing can misdirect conversations, trigger unnecessary tool usage, and increase the chance that downstream sub-skills perform sensitive actions in the wrong context.

Content

No source excerpt is available for this finding.